Skip to content
DraconiticResearch
Search Sources API
186,546 studies31 sourcesUpdated 51 min ago
Peer-reviewedCC BY-NC-NDJournal of Food Composition and Analysis

Geographical origin discrimination of Fructus Aurantii by visible near-infrared imaging with machine learning and explainable analysis

  • Mingkun Zhang1,2
  • Chao Ma1,2
  • Jianwei Ma1,2
  • Yunxia Yuan3
  • Jiayu Huang4
  • Mingtong Du5
5 affiliations
  1. 1College of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
  2. 2Guangdong HUST Industrial Technology Research Institute, Huazhong University of Science and Technology, Dongguan, 523808, Guangdong, China
  3. 3College of Food and Bioengineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
  4. 4College of Electronics and Information Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China
  5. 5College of Computing and Data Science, Nanyang Technological University, 639798, Singapore
Open at sourceDOICite

Abstract

Fructus Aurantii (FA), the dried processed product of Citrus aurantium L. , is widely used in food and functional food applications, and its quality is notably affected by geographical origin. In this study, a visible near-infrared (Vis/NIR) imaging platform was used to acquire reflectance images of FA samples from four production regions. An optimized and interpretable modeling framework was developed for FA origin discrimination by integrating spectral preprocessing, dimensionality reduction, machine learning classification, reinforcement-learning-inspired band selection, SOA-based XGBoost optimization, and quantitative SHAP analysis. The SOA-XGB model achieved an accuracy of 0.9213 ± 0.0148 in the four-class origin discrimination task and maintained stable performance on the external validation set. The band selection results showed that a limited number of informative wavelengths could achieve performance close to that of the full-band model. Quantitative SHAP analysis further indicated that wavelengths mainly distributed around 570–730 nm and 850–980 nm contributed notably to model decisions. These results demonstrate that Vis/NIR imaging combined with wavelength optimization, parameter optimization, and quantitative interpretability analysis provides a rapid, non-destructive, and reliable approach for FA geographical origin discrimination.

Related

  1. Explainable residual CNN with Gramian Angular Field encoding for rapid quantification of soil properties using near-infrared spectroscopy
    Xiong Li, Junwei Guo, Ran Wan +2
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textAnalytical chemistryCrossrefEurope PMCPMC
  2. NephroTox AI: an explainable machine learning framework with uncertainty quantification for drug-induced nephrotoxicity prediction
    Jixing Liu, Jiabing Guo, Henry H. Y. Tong +1
    Journal of CheminformaticsPeer-reviewedCC BY-NC-ND 4.0Theoretical & computational chemistryCrossref
  3. Explainable machine learning reveals a compact, low-dimensional geometric basis underlying sheet and skeletal TPMS architected materials
    Georgios Mermigkis, Chrysovalantis-Michail Liakopoulos, Dimitrios C. Rodopoulos +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMaterials & polymersCrossref
  4. Advancing specific local wine identification through integration of ICP-MS mineral wine profiles and Machine Learning: A case study on discrimination among the ten Beaujolais crus
    Yohann Clément, Pierre Lantéri, Agnès Hagège +6
    TalantaPeer-reviewedCC BY-NC-ND 4.0Full text2 citedGeneral biologyAnalytical chemistryHAL
  5. Machine Learning-Enhanced Solid-State Nanopore Analysis for Single-Molecule Discrimination of Albumin and Aptamer-Bound Glycated Albumin Complexes
    Harit Pitakjakpipop, Ibrar Alam, Kiatnida Treerattrakoon +13
    ACS OmegaPeer-reviewedCC BY-NC-ND 4.0Full textGeneral chemistryCrossref

Cite

BibTeXRIS
BibTeX
@article{zhang2026geographical,
  title = {{Geographical origin discrimination of Fructus Aurantii by visible near-infrared imaging with machine learning and explainable analysis}},
  author = {Mingkun Zhang and Chao Ma and Jianwei Ma and Yunxia Yuan and Jiayu Huang and Mingtong Du},
  journal = {Journal of Food Composition and Analysis},
  year = {2026},
  month = jun,
  doi = {10.1016/j.jfca.2026.109333},
  url = {https://doi.org/10.1016/j.jfca.2026.109333},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Geographical origin discrimination of Fructus Aurantii by visible near-infrared imaging with machine learning and explainable analysis
AU  - Mingkun Zhang
AU  - Chao Ma
AU  - Jianwei Ma
AU  - Yunxia Yuan
AU  - Jiayu Huang
AU  - Mingtong Du
PY  - 2026
DA  - 2026/06/23
JO  - Journal of Food Composition and Analysis
DO  - 10.1016/j.jfca.2026.109333
UR  - https://doi.org/10.1016/j.jfca.2026.109333
AB  - Fructus Aurantii (FA), the dried processed product of Citrus aurantium L. , is widely used in food and functional food applications, and its quality is notably affected by geographical origin. In this study, a visible near-infrared (Vis/NIR) imaging platform was used to acquire reflectance images of FA samples from four production regions. An optimized and interpretable modeling framework was developed for FA origin discrimination by integrating spectral preprocessing, dimensionality reduction, machine learning classification, reinforcement-learning-inspired band selection, SOA-based XGBoost optimization, and quantitative SHAP analysis. The SOA-XGB model achieved an accuracy of 0.9213 ± 0.0148 in the four-class origin discrimination task and maintained stable performance on the external validation set. The band selection results showed that a limited number of informative wavelengths could achieve performance close to that of the full-band model. Quantitative SHAP analysis further indicated that wavelengths mainly distributed around 570–730 nm and 850–980 nm contributed notably to model decisions. These results demonstrate that Vis/NIR imaging combined with wavelength optimization, parameter optimization, and quantitative interpretability analysis provides a rapid, non-destructive, and reliable approach for FA geographical origin discrimination.
SN  - 0889-1575
SN  - 1096-0481
ER  -